Legal claims defining the scope of protection, as filed with the USPTO.
1. A computer implemented method of selecting content object tags for recommendation to a user of a content hosting service, the method comprising: identifying a baseline subset of content objects within a content object corpus at the content hosting service based on a user context at the content hosting service; identifying a targeted subset of the baseline subset of content objects based on the user context, wherein each content object in the targeted subset of content objects is associated with one or more tags; for each tag associated with the targeted subset of content objects: determining a targeted subset count score for the tag based on the number of content objects in the targeted subset of content objects tagged with the tag; determining a frequency normalization score for the tag based on the proportion of the targeted subset of content objects that are tagged with the tag relative to the proportion of the baseline subset of content objects that are tagged with the tag; determining a distribution score for the tag based on 1) a first ratio comprising a number of content objects in a top-ranked portion of the targeted subset of content objects to the total number of content objects in the targeted subset of content objects, 2) a second ratio comprising a number of content objects in the top-ranked portion of the targeted subset of content objects that are tagged with the tag to the total number of content objects in the targeted subset of content objects that are tagged with the tag, and 3) a third ratio based on a logarithm of the first ratio and a logarithm of the second ratio; and computing a weighted tag score for the tag by combining all of the targeted subset count score for the tag, the frequency normalization score for the tag, the distribution score for the tag, and one or more associated weight coefficients; and selecting one or more tags for recommendation to the user based on the determined weighted tag scores.
2. The method of claim 1 , wherein the user context comprises the browsing of content objects by the user.
3. The method of claim 2 , wherein the targeted subset of content objects comprises one or more of: content objects previously viewed by the user, content objects previously viewed by other users, and content objects related to content objects previously viewed by the user and/or other users.
4. The method of claim 1 , wherein the user context comprises the searching of content objects by the user.
5. The method of claim 4 , wherein the targeted subset of content objects comprises content object search results received in response to the searching of content objects by the user.
6. The method of claim 1 , wherein the user context comprises the uploading of a content object by the user, and wherein the user has tagged the uploaded content object with one or more tags.
7. The method of claim 6 , wherein the targeted subset of content objects comprises content objects other than the uploaded content object that are tagged with all or part of the one or more tags.
8. The method of claim 1 , wherein the computing of a weighted tag score for a tag comprises calculating a harmonic mean of the targeted subset count score for the tag, the frequency normalization score for the tag, and the distribution score for the tag.
9. The method of claim 1 , wherein one weight coefficient is associated with each of the targeted subset count scores, the frequency normalization scores, and the distribution scores.
10. The method of claim 9 , wherein the weight coefficients are pre-determined based on a desired relative importance of each of the targeted subset count scores, the frequency normalization scores, and the distribution scores.
11. The method of claim 1 , wherein selecting one or more tags for recommendation comprises: determining a quantity of tags to be recommended to the user based on available space within a user interface; and selecting the quantity of tags with the highest weighted tag scores for recommendation.
12. The method of claim 11 , further comprising: displaying the selected quantity of tags to the user within the user interface.
13. A non-transitory computer-readable storage medium having executable computer program instructions embodied therein for selecting content object tags for recommendation to a user of a content hosting service, the computer program instructions configured to, when executed, cause a computer to: identify a baseline subset of content objects within a content object corpus at the content hosting service based on a user context at the content hosting service; identify a targeted subset of the baseline subset of content objects based on the user context, wherein each content object in the targeted subset of content objects is associated with one or more tags; for each tag associated with the targeted subset of content objects: determine a targeted subset count score for the tag based on the number of content objects in the targeted subset of content objects tagged with the tag; determine a frequency normalization score for the tag based on the proportion of the targeted subset of content objects that are tagged with the tag relative to the proportion of the baseline subset of content objects that are tagged with the tag; determine a distribution score for the tag based on 1) a first ratio comprising a number of content objects in a top-ranked portion of the targeted subset of content objects to the total number of content objects in the targeted subset of content objects, 2) a second ratio comprising a number of content objects in the top-ranked portion of the targeted subset of content objects that are tagged with the tag to the total number of content objects in the targeted subset of content objects that are tagged with the tag, and 3) a third ratio based on a logarithm of the first ratio and a logarithm of the second ratio; and compute a weighted tag score for the tag by combining all of the targeted subset count score for the tag, the frequency normalization score for the tag, the distribution score for the tag, and one or more associated weight coefficients; and select one or more tags for recommendation to the user based on the determined weighted tag scores.
14. The non-transitory computer-readable storage medium of claim 13 , wherein the computing of a weighted tag score for a tag comprises calculating a harmonic mean of the targeted subset count score for the tag, the frequency normalization score for the tag, and the distribution score for the tag.
15. The non-transitory computer-readable storage medium of claim 13 , wherein one weight coefficient is associated with each of the targeted subset count scores, the frequency normalization scores, and the distribution scores.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the weight coefficients are pre-determined based on a desired relative importance of each of the targeted subset count scores, the frequency normalization scores, and the distribution scores.
17. The non-transitory computer-readable storage medium of claim 13 , wherein selecting one or more tags for recommendation comprises: determining a quantity of tags to be recommended to the user based on available space within a user interface; and selecting the quantity of tags with the highest weighted tag scores for recommendation.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the computer program instructions are further configured to cause a computer to: display the selected quantity of tags to the user within the user interface.
19. A computer system for selecting content object tags for recommendation to a user of a content hosting service, the system comprising: a computer processor; and a non-transitory computer-readable storage medium storing executable computer program instructions configured to, when executed by the processor, cause the computer system to: identify a baseline subset of content objects within a content object corpus at the content hosting service based on a user context at the content hosting service; identify a targeted subset of the baseline subset of content objects based on the user context, wherein each content object in the targeted subset of content objects is associated with one or more tags; for each tag associated with the targeted subset of content objects: determine a targeted subset count score for the tag based on the number of content objects in the targeted subset of content objects tagged with the tag; determine a frequency normalization score for the tag based on the proportion of the targeted subset of content objects that are tagged with the tag relative to the proportion of the baseline subset of content objects that are tagged with the tag; determine a distribution score for the tag based on 1) a first ratio comprising a number of content objects in a top-ranked portion of the targeted subset of content objects to the total number of content objects in the targeted subset of content objects, 2) a second ratio comprising a number of content objects in the top-ranked portion of the targeted subset of content objects that are tagged with the tag to the total number of content objects in the targeted subset of content objects that are tagged with the tag, and 3) a third ratio based on a logarithm of the first ratio and a logarithm of the second ratio; and compute a weighted tag score for the tag by combining all of the targeted subset count score for the tag, the frequency normalization score for the tag, the distribution score for the tag, and one or more associated weight coefficients; and select one or more tags for recommendation to the user based on the determined weighted tag scores.
20. The computer system of claim 19 , wherein the computing of a weighted tag score for a tag comprises calculating a harmonic mean of the targeted subset count score for the tag, the frequency normalization score for the tag, and the distribution score for the tag.
21. The computer system of claim 19 , wherein one weight coefficient is associated with each of the targeted subset count scores, the frequency normalization scores, and the distribution scores.
22. The computer system of claim 21 , wherein the weight coefficients are pre-determined based on a desired relative importance of each of the targeted subset count scores, the frequency normalization scores, and the distribution scores.
23. The computer system of claim 19 , wherein selecting one or more tags for recommendation comprises: determining a quantity of tags to be recommended to the user based on available space within a user interface; and selecting the quantity of tags with the highest weighted tag scores for recommendation.
24. The computer system of claim 23 , wherein the computer program instructions are further configured to cause the computer system to: display the selected quantity of tags to the user within the user interface.
25. A computer implemented method of selecting content object tags for recommendation to a user of a content object hosting service, the method comprising: identifying a set of content objects based on a user context at the content object hosting service, wherein each content object is tagged with one or more tags; for each of the tags used to tag the content objects in the set of content objects: determining a targeted subset count score for the tag based on the number of content objects in the set of content objects tagged with the tag; determining a frequency normalization score for the tag based on the proportion of content objects in the set of content objects tagged with the tag relative to the proportion of all content objects at the content object hosting service tagged with the tag; determining a distribution score for the tag based on 1) a first ratio comprising a number of content objects in a top-ranked portion of the set of content objects to the total number of content objects in the set of content objects, 2) a second ratio comprising a number of content objects in the top-ranked portion of the set of content objects that are tagged with the tag to the total number of content objects in the set of content objects that are tagged with the tag, and 3) a third ratio based on a logarithm of the first ratio and a logarithm of the second ratio; and computing a weighted tag score for the tag by combining all of the targeted subset count score for the tag, the frequency normalization score for the tag, the distribution score for the tag, and one or more associated weight coefficients; and selecting one or more tags for recommendation to the user based on the determined weighted tag scores.
Unknown
December 13, 2016
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.